Journal of the Institute of Electronics Engineers of Korea CI (전자공학회논문지CI)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

Extensions of Knowledge-Based Artificial Neural Networks for the Theory Refinements

영역이론정련을 위한 지식기반신경망의 확장

  • Shim, Dong-Hee (Jeonju University, School of Information Technology and Computer Engineering)
  • 심동희 (전주대학교 정보기술 컴퓨터공학부)
  • Published : 2001.11.25
Download PDF
⟨ Previous Next ⟩

Abstract

KBANN (knowledge-based artificial neural network) combining the analytical learning and the inductive learning has been shown to be more effective than other machine learning models. However KBANN doesn't have the theory refinement ability because the topology of network can't be altered dynamically. Although TopGen was proposed to extend the ability of KABNN in this respect, it also had some defects. The algorithms which could solve this TopGen's defects, enabling the refinement of theory, by extending KBANN, are designed.

분석적학습과 귀납적학습을 결합한 지식기반신경망은 다른 기계학습모델보다 우수한 성능을 나타내고 있다. 그러나 지식기반신경망에서는 신경망이 형성된 후 그 구조를 동적으로 변경할 수 없어서 영역이론정련화 기능을 제공하지 못한다. 이러한 단점을 갖고 있는 지식기반신경망을 보완하기 위하여 TopGen 알고리즘이 제안되었지만 부분적인 문제점을 안고 있다. 본 논문에서는 TopGen의 문제점을 해소하면서 지식기반 신경망을 확장하여 영역이론정련기능을 부여하는 방안 2가지를 제시하고 이를 평가하였다.

Keywords

References

  1. S. B. Thrun and T. M. Mitchell, 'Integrating Inductive Neural Network Learning and Explanation-Based Learning', In Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence, pp. 930-936, 1993
  2. J. W. Shavlik and G. G. Towell, 'An Approach to Combining Explanation-based and Neural Learning Algorithms', Connection Science, Vol.1, No. 3, pp. 233-255, 1989
  3. D. W. Opitz, 'An Anytime Approach to Connectionist Theory Refinement：Refining the Topologies of Knowledge-Based Neural Networks', PhD thesis, University of Wisconsin-Madison, 1995
  4. D. Ourston and R. Mooney, 'Theory Refinement Combining Analytical and Empirical Methods', Artificial Intelligence, Vol.66, pp. 273-309, 1994 https://doi.org/10.1016/0004-3702(94)90028-0
  5. G. G. Towell, & J. W. Shavlik and M. Noordewier, 'Refinement of Approximate domain theories by Knowledge-based Neural Networks', In Proc. of the 8th National Conference on Artificial Intelligence, pp. 861-866, Boston, MA, 1990
  6. D.W. Opitz, and J. W. Shavlik , 'Heuristically Expanding Knowledge-Based Neural Networks', In Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence,1993, pp. 1360-365, 1993
  7. G.G. Towell, 'Symbolic Knowledge and Neural Networks：Insertion, Refinement, and Extraction', PhD thesis, University of Wisconsin-Madison, 1991
  8. G. G. Towell, & J. W. Shavlik, 'Using Symbolic Learning to Improve Knowledge-Based Neural Networks', Proceedings of AAAI, pp.177-182, 1992
  9. D.E. Rumelhart, G.E.Hinton, and J. R. Williams, 'Learning Internal Representations by Error Propagation', Vol. 1, pp. 318-363, MIT press, 1986